© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4110
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax elements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code and text snippets

    np_acts-logits-general · gemini-2.0-flash

    code and text delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.78
    __(/*!
    -0.77
     يتيمه
    -0.77
     pinulongan
    -0.75
    нгред
    -0.75
    richTextPanel
    -0.74
    tagHelperRunner
    -0.73
    脚注の使い方
    -0.72
     ddelweddau
    -0.72
     Taktlose
    -0.70
    POSITIVE LOGITS
    :
    0.44
     guess
    0.37
     think
    0.35
     will
    0.35
     view
    0.35
    :%.
    0.35
    :\
    0.34
    -
    0.34
     sample
    0.33
    __':
    0.33
    Activations Density 0.067%

    No Known Activations